artifact
active
artifact:claude-sonnet-4-5

Claude Sonnet 4.5

Mid-tier LLM from Anthropic evaluated with n=14 games.

Neighborhood — ranked by edge-count

Datasets (1)

dataset
  • Multi-turn conversation dataset
    uses
    Dataset of 240 multi-turn conversations per model between target models and Claude Sonnet 4.5 as simulated human, used to measure probe persistence